Skip to Main Content

Immune-Harness

The Harness Engineering & Model Wrangling Hackathon
docs.google.com/…

Can we stop AI agents from going rogue before they take over the world? Immune Harness is a security layer for AI agents. It checks every tool call before it runs and blocks the risky ones. When Jev catches a new attack, the harness writes a new policy, or rewrites an existing one to cover the new variant, and tests it before it goes live. Every attack it blocks makes it stronger, so the next attempt is stopped instantly. Powered by Jev for risk detection and MongoDB Atlas for live policy updates shared across every agent.

Team

javie32

Placement

Participant

More from The Harness Engineering & Model Wrangling Hackathon

Ripple

Ripple designs circuit boards from plain English, grades them against hidden checks, and evolves its own harness from the failures, going from 0/4 to 3/4 on…

Ripple project preview

Offload

Offload learns the work you repeat, so next time you can hand it over. Its engine, REM (Replay · Evolve · Merge), is an agent harness with a day/night cycle…

Offload project preview

Morgadarsha

Recursive Computer Use is a local-first desktop automation harness that enables AI agents to execute tasks on your computer, verify outcomes locally, and…

Morgadarsha project preview

Da Vinci: Recursive Improvement CAD Harness

Da Vinci is a recursive improvement CAD harness designed to support physical engineering tasks through specialized AI agents, programmatic CAD and automated…

Da Vinci: Recursive Improvement CAD Harness project preview

CyclopsDiary

CyclopsDiary gives factory workers wearing Meta AI glasses a shared memory of the floor. Every worker's glasses feed one MongoDB memory that keeps what was…

CyclopsDiary project preview

Sightline

A harness that teaches itself what context to show Jev, TypeSafe's fast decision model, proves the result on a storm it never saw, and can't cheat because…

www.loom.com/…